Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 117573
    Prev
    Next
    INDEX
    Explanations

    colonization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Integrated
    -0.08
     Carr
    -0.08
    atid
    -0.08
     Integrated
    -0.08
    .grad
    -0.07
    entication
    -0.07
     infatti
    -0.07
    ී
    -0.07
     ryg
    -0.07
     tailored
    -0.07
    POSITIVE LOGITS
     Voyage
    0.09
     beaches
    0.09
    不了
    0.08
     niches
    0.07
     seize
    0.07
     udp
    0.07
     comprend
    0.07
     emojis
    0.07
     establish
    0.07
     shores
    0.07
    Activations Density 0.003%

    No Known Activations